{"id":4399,"date":"2025-06-06T07:02:25","date_gmt":"2025-06-06T07:02:25","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/06\/06\/2506-04626\/"},"modified":"2025-06-06T07:02:25","modified_gmt":"2025-06-06T07:02:25","slug":"2506-04626","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/06\/06\/2506-04626\/","title":{"rendered":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning"},"content":{"rendered":"

Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2506.04626v1 Announce Type: new
\nAbstract: Motivated by real-world settings where data collection and policy deployment — whether for a single agent or across multiple agents — are costly, we study the problem of on-policy single-agent reinforcement learning (RL) and federated RL (FRL) with a focus on minimizing burn-in costs (the sample sizes needed to reach near-optimal regret) and policy switching or communication costs. In parallel finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states and $A$ actions, existing methods either require superlinear burn-in costs in $S$ and $A$ or fail to achieve logarithmic switching or communication costs. We propose two novel model-free RL algorithms — Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost — that are the first in the literature to simultaneously achieve: (i) the best near-optimal regret among all known model-free RL or FRL algorithms, (ii) low burn-in cost that scales linearly with $S$ and $A$, and (iii) logarithmic policy switching cost for single-agent RL or communication cost for FRL. Additionally, we establish gap-dependent theoretical guarantees for both regret and switching\/communication costs, improving or matching the best-known gap-dependent bounds.<\/div>\n

\t

\n
<\/BR>
\n Haochen Zhang, Zhong Zheng, Lingzhou Xue
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning arXiv:2506.04626v1 Announce Type: new Abstract: Motivated by real-world settings where data collection and policy deployment — whether for a single agent or across multiple agents — are costly, we study the problem of on-policy single-agent reinforcement learning (RL) and federated RL (FRL) with a […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,112],"tags":[1659,199,660],"class_list":["post-4399","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-cost","tag-learning","tag-regret"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/4399"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=4399"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/4399\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=4399"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=4399"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=4399"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}